{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/using-millions-of-emoji-occurrences-to-learn","title":"Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm","arxiv_id":"1708.00524","date":"2017-08-01","proceeding":"EMNLP 2017 9","authors":["Bjarke Felbo","Alan Mislove","Anders Søgaard","Iyad Rahwan","Sune Lehmann"],"abstract":"NLP tasks are often limited by scarcity of manually annotated data. In social\nmedia sentiment analysis and related tasks, researchers have therefore used\nbinarized emoticons and specific hashtags as forms of distant supervision. Our\npaper shows that by extending the distant supervision to a more diverse set of\nnoisy labels, the models can learn richer representations. Through emoji\nprediction on a dataset of 1246 million tweets containing one of 64 common\nemojis we obtain state-of-the-art performance on 8 benchmark datasets within\nsentiment, emotion and sarcasm detection using a single pretrained model. Our\nanalyses confirm that the diversity of our emotional labels yield a performance\nimprovement over previous distant supervision approaches.","url_abs":"http://arxiv.org/abs/1708.00524v2","url_pdf":"http://arxiv.org/pdf/1708.00524v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"using-millions-of-emoji-occurrences-to-learn","repo_url":"https://github.com/bfelbo/deepmoji","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"using-millions-of-emoji-occurrences-to-learn","repo_url":"https://github.com/Obs01ete/chatbot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"using-millions-of-emoji-occurrences-to-learn","repo_url":"https://github.com/SEntiMoji/SEntiMoji","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"using-millions-of-emoji-occurrences-to-learn","repo_url":"https://github.com/alexandra-chron/ntua-slp-wassa-iest2018","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"using-millions-of-emoji-occurrences-to-learn","repo_url":"https://github.com/alexandra-chron/wassa-2018","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"using-millions-of-emoji-occurrences-to-learn","repo_url":"https://github.com/huggingface/torchMoji","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"using-millions-of-emoji-occurrences-to-learn","repo_url":"https://github.com/lorenzofamiglini/Irony-Sarcasm-Detection-Task","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"sarcasm-detection","task_name":"Sarcasm Detection"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sentiment-analysis-on-1b-words","task":"Sentiment Analysis","dataset":"1B Words","model":"Random","rank_in_archive_order":1,"of":1,"metrics":{"1 in 10 R@1":"17"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-mr","task":"Sentiment Analysis","dataset":"MR","model":"Millions of Emoji","rank_in_archive_order":19,"of":19,"metrics":{"Training Time":"1500"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1708.00524","atlas_url":"https://app.syntology.ai/?focus=1708.00524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.00524"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alexandra-chron/wassa-2018","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SEntiMoji/SEntiMoji","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bfelbo/deepmoji","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alexandra-chron/ntua-slp-wassa-iest2018","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huggingface/torchMoji","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lorenzofamiglini/Irony-Sarcasm-Detection-Task","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Obs01ete/chatbot","reach":{"status":"unanswered"}}],"summary":{"ran_fixture":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"39f52ccce61314dd","entry":"top_elements","repo":"bfelbo/deepmoji","repo_kind":"official","path":"examples/score_texts_emojis.py","file_url":"https://github.com/bfelbo/deepmoji/blob/HEAD/examples/score_texts_emojis.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"39f52ccce61314dd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}